server: refactor child --> router communication (#24821)

* server: refactor child --> router communication

* fix wakeup case

* add docs

* improve update_status()

* nits
This commit is contained in:
Xuan-Son Nguyen
2026-06-20 01:02:26 +02:00
committed by GitHub
parent 4b48a53b6c
commit 2b686a9120
8 changed files with 173 additions and 91 deletions
+10 -1
View File
@@ -295,7 +295,16 @@ struct common_params_model {
std::string hf_repo = ""; // HF repo // NOLINT
std::string hf_file = ""; // HF file // NOLINT
std::string docker_repo = ""; // Docker repo // NOLINT
std::string name = ""; // in format <user>/<model>[:<tag>] (tag is optional) // NOLINT
std::string get_name() {
if (!hf_repo.empty()) {
return hf_repo;
}
if (!docker_repo.empty()) {
return docker_repo;
}
return path;
}
};
// draft-model-based speculative decoding parameters